A new framework for airborne minefield detection using Markov marked point processes

Aladin Research Commons

A new framework for airborne minefield detection using Markov marked point processes

Show full item record

Title: A new framework for airborne minefield detection using Markov marked point processes
Author: Trang, Anh
Abstract: Detecting both patterned and unpatterned minefields from an airborne platform is particularly challenging because of low signal contrast, high variability of mine signatures, relatively high density of man-made and natural clutter objects, and variability of minefield layouts. This dissertation is an investigation into how shape/spectral similarity of the mine signature and the minefield-like spatial distribution can be exploited simultaneously to improve the performance for patterned and unpatterned minefield detection in highly cluttered environments. The minefield decision is based on the detected targets obtained by an anomaly detector, such as the RX algorithm, in the image of a given field segment. Spectral, shape or texture features at the target locations are used to model the likelihood of the targets being potential mines. The spatial characteristic of the minefield structure is captured by the expected distribution of nearest neighbor distances of the detected mine locations. The clutter targets in the minefield are assumed to constitute a Poisson point process. The overall minefield detection problem is formulated as a Markov marked point process (MMPP) that is based on local attributes and relative spatial distribution of the target signatures. Minefield decision is formulated under binary hypothesis testing using maximum log-likelihood ratio. A quadratic heuristic search algorithm is developed to identify a set of detections that maximizes the minefield log-likelihood ratio. Furthermore, a procedure based on expectation maximization is developed for estimating unknown parameters like mine-level probability of detection and mine-to-mine separation. The minefield detection performance under this MMPP formulation is compared to baseline algorithm using simulated data. Results based on thousands of minefield and background segments show that the minefield performance based on MMPP formulation is much better than the performance of the baseline for both patterned and unpatterned minefields. An analytical solution for a detection problem is also derived. The minefield performance of analytical and simulated-based solutions based on the minefield likelihood values for three different clutter rates are compared.
Description: Degree awarded: Ph.D. Electrical Engineering and Computer Science. The Catholic University of America
URI: http://hdl.handle.net/1961/9319
Date: 2011-03-01

Files in this item

Files Size Format View
Trang_cua_0043A_10175display.pdf 2.386Mb PDF View/Open

This item appears in the following Collection(s)

Show full item record

Search DSpace

Advanced Search


My Account